A mid-protocol evaluation system is operable to receive a set of medical scans corresponding to a proper subset of a plurality of sequence types in a medical scan protocol captured for a patient. Abnormality data is generated by performing an inference function on the set of medical scans, where the inference function utilizes a computer vision model trained on a plurality of medical scans corresponding to the subset of the plurality of sequence types. A confidence score for the abnormality data is calculated, and additional sequence necessity data is generated for transmission to a client device for display via a display device. The additional sequence necessity data indicates at least one additional medical scan is necessary when the confidence score compares unfavorably to a confidence score threshold. The additional sequence necessity data indicates no further medical scans are necessary when the confidence score compares favorably to the confidence score threshold.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A mid-protocol evaluation system comprising: at least one processor; and a memory that stores operational instructions that, when executed by the at least one processor, cause the mid-protocol evaluation system to: receive, via a receiver, a set of medical scans corresponding to a proper subset of a plurality of sequence types in a medical scan protocol captured for a patient; generate abnormality data by performing an inference function on the set of medical scans, wherein the inference function utilizes a computer vision model trained on a plurality of medical scans corresponding to the proper subset of the plurality of sequence types; calculate a confidence score for the abnormality data; generate first additional sequence necessity data, wherein the first additional sequence necessity data indicates at least one first additional medical scan of the patient, corresponding to a first at least one of the plurality of sequence types not included in the proper subset of the plurality of sequence types, is necessary when the confidence score compares unfavorably to a confidence score threshold, and wherein the first additional sequence necessity data indicates no further medical scans of the patient are necessary when the confidence score compares favorably to the confidence score threshold; and transmit, via a transmitter, a notification indicating the additional sequence necessity data to a client device for display via a display device.
2. The mid-protocol evaluation system of claim 1 , wherein the first additional sequence necessity data indicates the at least one first additional medical scan of the patient is necessary, wherein the computer vision model is further trained on an additional plurality of medical scans corresponding to the first at least one of the plurality of sequence types, wherein the at least one first additional medical scan of the patient is performed as a result of the notification, and wherein the operational instructions, when executed by the at least one processor, further cause the mid-protocol evaluation system to: receive, via the receiver, the at least one first additional medical scan; generate updated abnormality data by performing the inference function on the at least one first additional medical scan; calculate an updated confidence score for the updated abnormality data; generate second additional sequence necessity data, wherein the second additional sequence necessity data indicates at least one second additional medical scan of the patient, corresponding to a second at least one of the plurality of sequence types that is not included in the proper subset of the plurality of sequence types and is different from the first at least one of the plurality of sequence types, is necessary when the updated confidence score compares unfavorably to the confidence score threshold, and wherein the second additional sequence necessity data indicates no further medical scans of the patient are necessary when the updated confidence score compares favorably to the confidence score threshold; and transmit, via the transmitter, a second notification indicating the second additional sequence necessity data to the client device for display via the display device.
3. The mid-protocol evaluation system of claim 2 , wherein generating the updated abnormality data includes performing the inference function on an updated set of medical scans that includes the set of medical scans and the at least one first additional medical scan.
4. The mid-protocol evaluation system of claim 3 , wherein the abnormality data indicates a detected abnormality, and wherein the updated abnormality data no longer indicates the detected abnormality.
5. The mid-protocol evaluation system of claim 3 , wherein the abnormality data indicates no detected abnormalities, and wherein the updated abnormality data indicates at least one detected abnormality.
6. The mid-protocol evaluation system of claim 3 , wherein the updated confidence score is less favorable than the confidence score.
7. The mid-protocol evaluation system of claim 1 , wherein the first additional sequence necessity data indicates the at least one first additional medical scan of the patient is necessary, and wherein the operational instructions, when executed by the at least one processor, further cause the mid-protocol evaluation system to: select the first at least one of the plurality of sequence types from the plurality of sequence types based on the abnormality data.
8. The mid-protocol evaluation system of claim 7 , wherein the first at least one of the plurality of sequence types is selected from the plurality of sequence types based on a density value of an abnormality indicated in the abnormality data.
9. The mid-protocol evaluation system of claim 7 , wherein the first at least one of the plurality of sequence types is selected from the plurality of sequence types based on an anatomical location of an abnormality indicated in the abnormality data.
10. The mid-protocol evaluation system of claim 1 , wherein the first additional sequence necessity data indicates the at least one first additional medical scan of the patient is necessary, and wherein the operational instructions, when executed by the at least one processor, further cause the mid-protocol evaluation system to: select a different sequence type based on the abnormality data, wherein the at least one first additional medical scan indicated in the first additional sequence necessity data corresponds to the different sequence type, and wherein the different sequence type is not included in the plurality of sequence types of the medical scan protocol.
11. The mid-protocol evaluation system of claim 1 , wherein the set of medical scans correspond to a set of Magnetic Resonance Imaging (MM) scans, wherein the medical scan protocol corresponds to a MRI protocol, and wherein the plurality of sequence types includes at least one of: a T2 sequence, a T1 sequence, a diffusion sequence, or a fluid attenuated inversion recovery (FLAIR) sequence.
12. The mid-protocol evaluation system of claim 1 , wherein the set of medical scans were captured by a medical imaging machine, wherein the first additional sequence necessity data indicates the at least one first additional medical scan of the patient is necessary, wherein the notification is transmitted to the medical imaging machine, and wherein the medical imaging machine automatically performs the at least one first additional medical scan of the patient in response to receiving the notification.
13. The mid-protocol evaluation system of claim 1 , wherein the set of medical scans were captured by an medical imaging machine, wherein the medical imaging machine is scheduled to execute a task that includes generating medical scans for the patient corresponding to all of a remaining subset of the plurality of sequence types, wherein the first additional sequence necessity data indicates the no further medical scans of the patient are necessary, wherein the notification is transmitted to the medical imaging machine, and wherein the medical imaging machine automatically ceases execution of the task in response to receiving the notification.
14. The mid-protocol evaluation system of claim 1 , wherein the set of medical scans includes at least two medical scans, wherein each of the set of medical scans are captured by a medical imaging machine in an order, one at a time, wherein the each of the set of medical scans are received, in separate transmissions, by the mid-protocol evaluation system in accordance with the order, wherein the inference function is performed in response to receiving the each of the set of medical scans to calculate the confidence score for the each of the set of medical scans, wherein each subsequent one of the set of medical scans in the order are captured by the medical imaging machine in response to the client device receiving a corresponding one of a set of notifications that includes additional sequence necessity data indicating the each subsequent one of the set of medical scans, and wherein each of the set of notifications are transmitted by the mid-protocol evaluation system in response to the confidence score calculated for the each of the set of medical scans comparing unfavorably to the confidence score threshold.
15. The mid-protocol evaluation system of claim 14 , wherein the mid-protocol evaluation system determines an optimal ordering of the plurality of sequence types in a medical scan protocol prior to capturing of the set of medical scans by the medical imaging machine, wherein the optimal ordering is transmitted to the client device, wherein the set of medical scans are captured by the medical imaging machine in accordance with the optimal ordering, and wherein the set of medical scans are received the mid-protocol evaluation system in accordance with the optimal ordering.
16. The mid-protocol evaluation system of claim 1 , wherein the set of medical scans correspond to a set of Magnetic Resonance Imaging (MM) scans, wherein the medical scan protocol corresponds to a MRI protocol, wherein the MM protocol is one of a plurality of MRI protocols, and wherein each of the plurality of MRI protocols is associated with one of a set of anatomical regions, wherein each of the plurality of MRI protocols is further associated with one of a set of medical conditions in the one of a set of anatomical regions, and wherein the operational instructions, when executed by the at least one processor, further cause the mid-protocol evaluation system to: receive, via the receiver, patient symptom data corresponding the patient prior to capturing of the set of medical scans by a medical imaging machine; select the MRI protocol from the plurality of MM protocols by performing a second inference function on the patient symptom data, wherein the second inference function was trained on a set of patient symptom data and a corresponding set of diagnosed medical conditions; and transmit, via the transmitter, the MM protocol to the client device, wherein the set of medical scans are captured by a medical imaging device in response to the client device receiving the MRI protocol.
17. The mid-protocol evaluation system of claim 1 , wherein the first additional sequence necessity data indicates the no further medical scans of the patient are necessary, and wherein the operational instructions, when executed by the at least one processor, further cause the mid-protocol evaluation system to: transmit, via the transmitter, the abnormality data to the client device for display via the display device in response to the first additional sequence necessity data indicating the no further medical scans of the patient are necessary.
18. The mid-protocol evaluation system of claim 17 , wherein the display device further displays image data of the set of medical scans, wherein the abnormality data is displayed by the client device, overlaid upon the image data of the set of medical scans, to visually indicate at least one abnormality detected in the image data.
19. The mid-protocol evaluation system of claim 17 , wherein the abnormality data indicates that the set of medical scans contains no abnormalities.
20. A method for execution by a mid-protocol evaluation system, comprising: receiving, via a receiver, a set of medical scans corresponding to a proper subset of a plurality of sequence types in a medical scan protocol captured for a patient; generating abnormality data by performing an inference function on the set of medical scans, wherein the inference function utilizes a computer vision model trained on a plurality of medical scans corresponding to the proper subset of the plurality of sequence types; calculating a confidence score for the abnormality data; generating first additional sequence necessity data, wherein the first additional sequence necessity data indicates at least one first additional medical scan of the patient, corresponding to a first at least one of the plurality of sequence types not included in the proper subset of the plurality of sequence types, is necessary when the confidence score compares unfavorably to a confidence score threshold, and wherein the first additional sequence necessity data indicates no further medical scans of the patient are necessary when the confidence score compares favorably to the confidence score threshold; and transmitting, via a transmitter, a notification indicating the additional sequence necessity data to a client device for display via a display device.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 18, 2019
December 29, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.